Nitro-E
amd基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
言語から画像、オープンウェイトからAPIまで。能力と実際の費用を比較。
次のアイデアに合うAIを見つけましょう。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
The model was quantized from Qwen/Qwen3.5-397B-A17B-FP8 using AMD-Quark. The weights are quantized to MXFP4 and activations are quantized to MXFP4. For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers. The GSM8K results were obtained using the vLLM framework, based on the Docker image `rocm/vllm-dev:nightly_main_20260211`, and vLLM is installed inside the container.
翻訳待ち・原文を表示
This checkpoint extends the routed-expert MXFP4 quantization by **also quantizing the shared expert to MXFP4 and fusing it into the routed MoE kernel** (FSE: fused shared expert). Compared with keeping the shared expert in bf16, this further reduces the bf16 footprint and improves decode throughput, with no measurable accuracy loss on GSM8K (see Evaluation). The model was quantized from Qwen/Qwen3.5-397B-A17B using AMD-Quark. Weights and activations are quantized to OCP MXFP4. For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers.
翻訳待ち・原文を表示
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
- **Model Architecture:** Qwen3_5MoeForCausalLM - **Input:** Text - **Output:** Text - **Supported Hardware Microarchitecture:** AMD MI350 / MI355 - **ROCm**: 7.2.0 - **PyTorch**: 2.12.0 - **Transformers**: 5.14.1 - **Operating System(s):** Linux - **Inference Engine:** SGLang/vLLM - **Model Optimizer:** AMD-Quark (v0.12) - **Quantized layers:** router experts - **Weight quantization:** OCP MXFP4, Static - **Activation quantization:** OCP MXFP4, Dynamic The model was quantized from Qwen/Qwen3.8-2.4T-A95B-FP8 using AMD-Quark. The weights and activations of the routed experts are quantized to MXFP4. For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers.
翻訳待ち・原文を表示
INT4 weight-only (W4A16) quantized version of `Qwen/Qwen3.8-27B`, produced with the **AWQ** algorithm using AMD Quark. \* BFCL Overall Acc reflects only `single_turn` categories, not the full Gorilla-leaderboard formula (multi-turn/web-search/memory categories were not run and would count as 0 against the public leaderboard's own Overall Acc). Sub-metrics: Non-Live AST 86.58% (base 88.52%), Live AST 81.57% (base 83.05%), Relevance Detection 75.00% (base 75.00%), Irrelevance Detection 72.47% (base 72.22%). Recovery % = quantized / BF16-base, using flexible-extract for GSM8K rows and base/quantized (inverted, since lower is better) for perplexity — both measured by us against verified-upstream `Qwen/Qwen3.8-27B` weights, not vendor-reported numbers. GSM8K uses `lm-evaluation-harness`; non-thinking mode is approximated by pre-closing an empty ` ` block in the prompt, since the harness task is a raw few-shot completion rather than a chat-templated request. BFCL run via the official `bfcl_eval` harness.
翻訳待ち・原文を表示
- **Weights:** MXFP4 (OCP microscaling FP4, group size 32, E8M0 shared scale) - **Activations:** MXFP4, dynamic (per-block, computed at runtime) - **Algorithm:** AWQ - **Calibration:** 128 samples, seq_len 512, `pileval` dataset (Quark default) - **Base model:** Qwen/Qwen3.8-27B (bf16) - **Vision tower:** left unquantized (bf16) — only the language-model decoder (`model.language_model.layers`) is quantized; `model.visual.*` is excluded Recovery % is computed on the flexible-extract metric (`this model / bf16 base`). Non-thinking mode: the raw-completions endpoint used above doesn't support passing `enable_thinking=False` through a chat template, so non-thinking mode is approximated with a custom task that pre-closes an empty ` ` block in the prompt:
翻訳待ち・原文を表示
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
This checkpoint quantizes the routed **and** shared MoE experts to OCP MXFP4 and keeps everything else in bf16, including the full self-attention and the (Mamba-style) linear-attention projections, the MTP head, router gates, shared-expert gate, PLE n-gram path, vision tower, hyper-connection mixers, and `lm_head`. The model was quantized from Qwen3.8-Flash-Next using AMD-Quark. MoE expert weights and activations are quantized to OCP MXFP4. The GSM8K results were obtained using the vLLM framework, based on the Docker image `vllm/vllm-openai-rocm:v0.32.0`, with lm-eval installed from source. This Reproduction serves the model without MTP. Enabling MTP on the formal `v0.32.0` release currently requires vLLM PR #61770.
翻訳待ち・原文を表示
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
提供元・分類・入出力の条件を変更してください。新しいモデルを随時追加しています。
月間トークン数を調整してAPI費用を比較。
収集済みの比較可能な100万トークン当たり米ドル料金です。キャッシュ割引、段階料金、追加推論出力、税金は含みません。最新料金は出典で確認してください。
入力・出力・キャッシュ料金を分け、同じ用途と使用量で総費用を比較します。画像・音声・動画は枚数、時間、解像度で課金される場合があります。
必ずしもそうではありません。バージョンごとのライセンス、商用制限、ポリシーを確認してください。自前運用には計算資源と保守費用も必要です。
順位はテスト、バージョン、評価方法によります。実際の業務データで精度、遅延、安定性、費用を比較してください。